Distributed dialogue policies for multi-domain statistical dialogue management

By Milica Gasic, Dongho Kim, Pirros Tsiakoulis, Susannah Young. 2015

48 citations recorded by the source corpus.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jianfeng Gao
2. Bing Liu
3. Lihong Li
4. Milica Gasic
5. Pei-hao Su
6. Xiujun Li
7. Maxine Eskénazi
8. Baolin Peng

Citations in the corpus

• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (2015, methodology): “To form a training corpus for each domain, dialogues collected from a previous user trial (Gaˇsi´c et al., 2015) of a statistical dialogue manager were randomly sampled and shown to workers recruited via the Amazon Mechanical Turk (AMT) service.”
• Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning (2017, background): “This requirement makes most of the existing methods of learning multi-domain dialogue agents (Cuay´ahuitl, 2009; Gasic et al., 2015b) inapplicable: these methods train a collection of policies, one for each domain, and there is no cross-domain constraints required to successfully complete a…”
• Policy committee for adaptation in multi-domain spoken dialogue systems (2015, background): “Index Terms— Bayesian committee machines, Gaussian processes, reinforcement learning”
• Learning Domain-Independent Dialogue Policies via Ontology Parameterisation (2015, methodology): “…rules (Wang and Lemon, 2013; Sun et al., 2014) and delexicalised deep classifiers (Henderson et al., 2014; Mrkˇsi´c et al., 2015) for dialogue state tracking, and domain-extensible/transferable statistical dialogue policies (Lemon et al., 2006; Gaˇsi´c et al., 2013; Gaˇsi´c et al., 2015).”
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability (2017, background): “Moreover, there has been an increased interest in extending task-oriented systems to multiple topics (Lee et al., 2009; Gaˇsi´c et al., 2015b) and multiple skills, e.g. grouping heterogeneous types of dialogs into a single sys-tem (Zhao et al., 2016).”